Abstract

Concrete compressive strength (CCS) is a key factor that affects the structural service life of structure. Laboratory testing is time consuming, costly, and restricted in applicability for the mix designs. Machine learning (ML) has emerged as a potential alternative to laboratory testing, based upon understanding the non-linear interaction of the variables for the mix design and CCS. This study builds a stacked ensemble (meta-learning) approach for eight distinct machine learning algorithms: Linear Regression, Tree, Random Forest, Gradient Boosting, AdaBoost, K Nearest Neighbors, Support Vector Machine, and Neural Networks. The UCI benchmark dataset (1,030 examples) with eight features (cement, blast furnace slag, fly ash, water, superplasticizer, coarse/fine aggregates, age) and CCS as the target was analyzed. 70/30 splits for train and test sets and multi, level k-fold cross, validation (2–20 folds) were employed for robustness. Analysis of model performance was mainly carried out using R² permutation, based feature importances and one way ANOVA for the categorical variable age. The stacked model resulted in the best overall R²=0.890 (20, fold CV) compared to the best singles' performances (random forest: R²=0.878, gradient boosting: R²=0.874). Graphs for the predicted and actual CCS confirmed a very close fit (variations < 7 MPa). The cross validated model's overall features' importances were dominated by cement, age, and water, which was confirmed using the resulting ANOVA for age influence. As a spin-off, a convenient standalone software for the proposed framework also exists for real-time CCS strength predictions. The standalone application and trained models developed in this study will be made publicly available upon paper acceptance at: https://github.com/tufailmab/ccs-ensemble-predictor

References

1. K. Parida, L. Satpathy, A. N. Nayaka, and M. K. Amat, “Use of machine learning models for prediction of compressive strength of concrete produced with waste materials,” Innovative Infrastructure Solutions, vol. 10, no. 10, Oct. 2025, doi: 10.1007/S41062-025-02266-6.
2. M. Nafiuzzaman, T. I. Jakir, I. J. Aditi, A. Kabir, and K. A. Ahsan, “Different machine learning approaches to predict the compressive strength of composite cement concrete,” Journal of Building Pathology and Rehabilitation, vol. 10, no. 2, Dec. 2025, doi: 10.1007/S41024-025-00598-5.
3. M. C. Kang, D. Y. Yoo, and R. Gupta, “Machine learning-based prediction for compressive and flexural strengths of steel fiber-reinforced concrete,” Constr Build Mater, vol. 266, Jan. 2021, doi: 10.1016/J.CONBUILDMAT.2020.121117.
4. D. C. Feng et al., “Machine learning-based compressive strength prediction for concrete: An adaptive boosting approach,” Constr Build Mater, vol. 230, Jan. 2020, doi: 10.1016/J.CONBUILDMAT.2019.117000.
5. R. K. Tipu, V. R. Panchal, and K. S. Pandya, “Multi-objective optimized high-strength concrete mix design using a hybrid machine learning and metaheuristic algorithm,” Asian Journal of Civil Engineering, vol. 24, no. 3, pp. 849–867, Apr. 2023, doi: 10.1007/S42107-022-00535-8.
6. I. Albaijan et al., “Estimating the initial fracture energy of concrete using various machine learning techniques,” Eng Fract Mech, vol. 295, Jan. 2024, doi: 10.1016/J.ENGFRACMECH.2023.109776.
7. A. R. Al-Shamasneh et al., “Application of machine learning techniques to predict the compressive strength of steel fiber reinforced concrete,” Scientific Reports 2025 15:1, vol. 15, no. 1, pp. 30674-, Aug. 2025, doi: 10.1038/s41598-025-16516-1.
8. H. Ayat, Y. Kellouche, M. Ghrici, and B. Boukhatem, “Compressive strength prediction of limestone filler concrete using artificial neural networks,” Advances in Computational Design, vol. 3, no. 3, pp. 289–302, Jul. 2018, doi: 10.12989/ACD.2018.3.3.289.
9. H. Nguyen, T. Vu, T. P. Vo, and H. T. Thai, “Efficient machine learning models for prediction of concrete strengths,” Constr Build Mater, vol. 266, Jan. 2021, doi: 10.1016/J.CONBUILDMAT.2020.120950.
10. M. Mirrashid and H. Naderpour, “Recent Trends in Prediction of Concrete Elements Behavior Using Soft Computing (2010–2020),” Archives of Computational Methods in Engineering, vol. 28, no. 4, pp. 3307–3327, Jun. 2021, doi: 10.1007/S11831-020-09500-7.
11. N. D. Hoang and D. V. Tran, “Machine Learning-Based Estimation of Concrete Compressive Strength: A Multi-Model and Multi-Dataset Study,” Civil Engineering Infrastructures Journal, vol. 57, no. 2, pp. 247–265, Dec. 2024, doi: 10.22059/CEIJ.2023.354679.1910.
12. A. K. P Das, “Hybrid machine learning approach to prediction of the compressive and flexural strengths of UHPC and parametric analysis with shapley additive explanations,” Case Stud. Constr. Mater., vol. 20, p. e02723, 2024.
13. B. K. A. Mohamad Ali Ridho, C. Ngamkhanong, Y. Wu, and S. Kaewunruen, “Recycled aggregates concrete compressive strength prediction using artificial neural networks (ANNs),” Infrastructures (Basel), vol. 6, no. 2, p. 17, Feb. 2021, doi: 10.3390/infrastructures6020017.
14. H. Alabduljabbar, “Predicting ultra-high-performance concrete compressive strength using gene expression programming method,” Case Stud. Constr. Mater., vol. 18, p. e02074, 2023.
15. H. Naderpour, A. H. Rafiean, and P. Fakharian, “Compressive strength prediction of environmentally friendly concrete using artificial neural networks,” J. Build. Eng., vol. 16, pp. 213–219, Mar. 2018, doi: 10.1016/j.jobe.2018.01.007.
16. R. Kumar, D. R. Kumar, W. Wipulanusat, C. Thongchom, P. Samui, and B. Rai, “Estimation of the compressive strength of ultrahigh performance concrete using machine learning models,” Intell. Syst. Appl., vol. 25, pp. 2667–3053, Mar. 2025, doi: 10.1016/j.iswa.2024.200471.
17. P. G. Asteris, A. D. Skentou, A. Bardhan, P. Samui, and K. Pilakoutas, “Predicting concrete compressive strength using hybrid ensembling of surrogate machine learning models,” Cem Concr Res, vol. 145, Jul. 2021, doi: 10.1016/J.CEMCONRES.2021.106449.
18. P. G. Asteris and V. G. Mokos, “Concrete compressive strength using artificial neural networks,” Neural Comput. Appl., vol. 32, no. 15, pp. 11807–11826, Aug. 2020, doi: 10.1007/s00521-019-04663-2.
19. M. F. Javed et al., “Applications of gene expression programming and regression techniques for estimating compressive strength of Bagasse ash-based concrete,” Crystals (Basel), vol. 10, no. 9, p. 737, Sep. 2020, doi: 10.3390/cryst10090737.
20. S. S. Chandra, R. Kumar, A. Arjunasamy, S. Galagali, A. Tantri, and S. R. Naganna, “Predicting the compressive strength of polymer-infused bricks: A machine learning approach with SHAP interpretability,” Sci. Rep., vol. 15, no. 1, p. 8090, Dec. 2025, doi: 10.1038/s41598-025-89606-9.
21. R. Biswas, “Efficient soft computing techniques for the prediction of compressive strength of geopolymer concrete,” Comput. Concr, vol. 28, pp. 221–232, 2021.
22. Z. Shen, A. F. Deifalla, P. Kamiński, and A. Dyczko, “Compressive Strength Evaluation of Ultra-High-Strength Concrete by Machine Learning,” Materials, vol. 15, no. 10, May 2022, doi: 10.3390/MA15103523.
23. Z. M. Yaseen et al., “Advances in engineering software predicting compressive strength of lightweight foamed concrete using extreme learning machine model,” Adv. Eng. Softw., vol. 115, pp. 112–125, Jan. 2018, doi: 10.1016/j.advengsoft.2017.09.004.
24. M. Shaaban, M. Amin, S. Selim, and I. M. Riad, “Machine learning approaches for forecasting compressive strength of high-strength concrete,” Scientific Reports 2025 15:1, vol. 15, no. 1, pp. 25567-, Jul. 2025, doi: 10.1038/s41598-025-10342-1.
25. M. M. Alsaadawi, M. K. Elshaarawy, and A. K. Hamed, “Concrete compressive strength classification using hybrid machine learning models and interactive GUI,” Innovative Infrastructure Solutions 2025 10:5, vol. 10, no. 5, pp. 198-, Apr. 2025, doi: 10.1007/S41062-025-01983-2.